arXiv Computation and Language

Demand-Side Measurement for Generative Engine Optimization: Constructing and Validating a Million-Persona, Intent-Annotated Buyer Corpus

arXiv AI
Sep 2

Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching

The paper describes a new approach for two‑sided service marketplaces that replaces fixed request forms with AI‑native probabilistic matching using large language models. It introduces an autoresearch loop that generates a provider‑side preference taxonomy for each occupation, iteratively refining candidate tag sets through a six‑rubric LLM judge and a seven‑critic panel. The system also maps legacy form questions back to the new taxonomy, enabling coverage assessment and human quality assurance.

By Kartik Ravisankar, Hojat Abdolanezhad, Daniel Capo, Sang Su Lee, Shishir Dash, Vijay Anand Raghavan
arXiv AI
Jul 24

Benchmarking the Personalization Capabilities of Large Language Models

arXiv:2607. 20471v1 Announce Type: new Abstract: Personalization, the act of varying a message to induce action from a specific receiver while keeping sender, channel, and time fixed, has a long tradition in psychology and marketing as a two-party problem in which sender and receiver have independent objectives.

By Ashutosh Srivastava, Siddharth Yedlapati, Vinay Aggarwal, Yaman Kumar Singla, Shashwat Dixit, Jitendra Ajmera, Balaji Krishnamurthy
arXiv Machine Learning
Oct 3

System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer

The study evaluates whether aggregated brand recommendation profiles can identify the language model that generated them. Using 6,475 responses from five deployed endpoints, a character‑n‑gram classifier accurately attributes single responses to the correct system (97.84% accuracy). However, when responses are aggregated into domain‑condition units, the classifier’s performance drops to 66.53%, and a forest model misclassifies all gift‑domain units, indicating that aggregated brand behaviour does not reliably reveal the underlying system.

By Dmitrij \.Zatuchin
arXiv AI
Aug 18

Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation

arXiv:2608. 15877v1 Announce Type: new Abstract: Search and recommendation serve a shared discovery objective but encode intent differently.

By Rui Wang, Jiazhou Wang, Zheng Wei, Chenglin Lu, Fangcheng Sun, Ivy Sun, Jin Sun, Hui Geng, Lillian Zhang, Chao Yang, Lei Chen, Shahin Sefati, Reem Helou, Joe Zhou, Babak Shakibi, Yiyi Pan, Bi Xue, Hong Yan, Shujian Bu
arXiv AI
Oct 28

Role-Augmented Intent-Driven Generative Search Engine Optimization

The paper introduces RAID, a Role-Augmented Intent-Driven Generative Search Engine Optimization method that improves web content visibility without needing target queries or GSE feedback. RAID infers a primary retrieval intent from source content, refines it through a 4W multi-role deep reflection on prospective searchers’ information needs, and jointly plans and rewrites the content. Evaluated on 100 samples and 500 queries, RAID outperforms nine GEO rewriting strategies, achieving higher relative improvement scores and effective optimization rates.

By Xiaolu Chen, Jie Bao, Haojie Wu, Zhen Chen, Liwei Pan, Yong Liao
arXiv AI
Nov 6

The Popular Get More Popular: Auditing Brand Bias in Generative Search

The paper audits brand bias in generative search, focusing on two dimensions: brand popularity bias and brand familiarity bias. It finds that dominant brands appear 1.4x to 2.8x more often than average brands in commercial queries, and that unfamiliar brand signatures significantly lower recommendation rank while fact-preserving rewrites have little effect. These results show that generative search engines reinforce a rich‑get‑richer dynamic, favoring established market leaders and creating a parametric barrier to entry that standard content optimization cannot overcome.

By Giorgio Monaco, Jacopo Lenti, Francesco Pierri
arXiv Computation and Language
Sep 28

ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker

ZooWork-ShopRanker is a family of open e‑commerce rerankers (0.6B, 4B, and 8B) that align with human shopping preferences by using large language models as preference oracles to generate training pairs. The flagship 8B model serves as a teacher for the smaller 4B and 0.6B models, which are further refined on judged pairs. A new benchmark, ShopRank‑Bench, contains ~10,000 private‑traffic preference pairs and shows that all ZooWork models outperform the strongest open reranker baseline and their own un‑aligned versions.

By Siqiao Xue, Shuxuan Liu, Ning Hu
arXiv Computation and Language
Oct 5

Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It

The paper investigates how large language model (LLM) agents exhibit source preference when selecting items in end‑to‑end search tasks across three domains. Across 12 agent models, each consistently favors certain sources and avoids others, even when items from disfavored sources better meet the user’s requirements. The study shows that revealing or hiding source identifiers influences selection, and that training rewards or missing information can create or mitigate these preferences.

By Jonghyun Song, Haewon Park, Jeonghoon Shim, Woojung Song, Yohan Jo
arXiv Computation and Language
Sep 25

Measuring Brand and Source Discovery under Repeated LLM Queries: A Finite-Sample Audit

The study audits large language model (LLM) outputs by measuring how well repeated queries recover a collected set of responses versus the full set of possible outputs. Using sample-based rarefaction on 4,500 responses from 50 buying questions across six configurations, the authors find historical-dictionary median recovery rates between 92.6% and 95.2%, which drop to 89.5%–94.7% after re‑adjudicating all candidate strings. Additional analyses with Gemini 3.1 Pro annotations and matched roster data confirm that recovery percentages vary with extraction methods, question selection, and the finite reference collection, underscoring the need for explicit measurement definitions and sensitivity analyses in LLM audits.

By Dmitrij \.Zatuchin
arXiv Computation and Language
Sep 17

"If I Had to Buy Just ONE: Galaxy S26 Ultra": Auditing AI-Generated Product Recommendations

arXiv:2609.18729v1 Announce Type: cross Abstract: Consumers increasingly use AI chatbots for advice on what to buy. With companies like OpenAI and Google monetising their AI through advertising, this...

By Lucas G. Uberti-Bona Marin, Thales Bertaglia, Giovanni Astante, Bram Rijsbosch, Gijs van Dijck, Anik\'o Hann\'ak, Gerasimos Spanakis, Konrad Kollnig